Airline selection prediction method and device, electronic equipment and storage medium

A forecasting method, forecasting device technology

Pending Publication Date: 2022-07-26
CTRIP TRAVEL NETWORK TECH SHANGHAI0
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to overcome the disadvantages of predicting airline selection probability by manual analysis in the prior art, which cannot quantify various influencing factors and low prediction accuracy, and provide a prediction method for airline selection and device, electronic device, storage medium

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Airline selection prediction method and device, electronic equipment and storage medium
  • Airline selection prediction method and device, electronic equipment and storage medium
  • Airline selection prediction method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] This embodiment provides a prediction method selected by an airline company, refer to figure 1 , the prediction method includes the following steps:

[0037] S1. Obtain the user behavior data of the flight of the target airline;

[0038] S2, extracting target data according to the user behavior data; wherein, the target data is data that affects the user's choice of an airline;

[0039] S3. Input the target data into the airline company selection prediction model;

[0040] S4. Determine the selection probability of the target airline according to the result output by the airline company selection prediction model;

[0041] The airline company selection prediction model is obtained by training based on a training data set, and the training data set includes historical user behavior data of flights of different airlines and correspondingly selected airlines. The historical user behavior data may specifically include user search data, user reservation data, and the like...

Embodiment 2

[0047] On the basis of Embodiment 1, this embodiment provides a prediction method selected by an airline company.

[0048] In an implementable solution, step S4 includes: calculating the selection probability of the target airline according to the selection probability of all flights in the target airline output by the airline selection prediction model.

[0049] Specifically, the selection probabilities of all flights in the target airline may be added to obtain the selection probability of the target airline. The accuracy of airline-selected forecasts can also be improved by:

[0050] (1) When building a training data set, add user portrait features (such as the user's gender, age, occupation, etc.), as well as the user's historical behavioral habits (such as the user's probability of selecting each airline within a certain historical period);

[0051] (2) Using algorithms with strong predictive ability such as GBDT (Gradient Boosting Decision Tree Algorithm), XGB (Extreme ...

Embodiment 3

[0078] This embodiment provides a prediction device for airline selection, refer to image 3 , the device includes:

[0079] The behavior data acquisition module 1 is used to acquire the user behavior data of the flight of the target airline;

[0080] A target data extraction module 2, configured to extract target data according to the user behavior data; wherein, the target data is data that affects the user's choice of an airline;

[0081] target data input module 3, for inputting the target data into the airline company selection prediction model;

[0082] a selection probability determination module 4, configured to determine the selection probability of the target airline according to the result output by the airline selection prediction model;

[0083] The airline company selection prediction model is obtained by training based on a training data set, and the training data set includes historical user behavior data of flights of different airlines and correspondingly s...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an airline selection prediction method and apparatus, an electronic device and a storage medium. The prediction method comprises the steps of obtaining user behavior data of a flight of a target airline; extracting target data according to the user behavior data; wherein the target data is data influencing the airline selection of the user; inputting the target data into an airline selection prediction model; determining the selection probability of the target airline according to a result output by the airline selection prediction model; wherein the airline selection prediction model is obtained by training based on a training data set, and the training data set comprises historical user behavior data of flights of different airlines and the correspondingly selected airlines. According to the method, the airline selection prediction model is used for predicting the airline selection probability of the user, the problem that quantification is difficult when an airline company manually analyzes multi-dimensional data influencing airline selection can be solved, and meanwhile the accuracy of an airline selection prediction result can be improved.

Description

technical field [0001] The invention relates to the field of computer technology, and in particular, to a prediction method and device, electronic equipment and storage medium for airline selection. Background technique [0002] With the increasing demand for air transportation in society, more and more airlines (referred to as airlines) are opening or adding routes to varying degrees, and the competition between different airlines is becoming more and more fierce. When users choose an airline, they are usually affected by various factors such as fare, aircraft type, and airline brand. At present, airlines mainly use manual analysis to predict the probability of users choosing an airline. However, this method has the problem that it is difficult to comprehensively consider all the influencing factors, resulting in low prediction accuracy. SUMMARY OF THE INVENTION [0003] The technical problem to be solved by the present invention is to overcome the defects of inability t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/02G06Q50/30G06N20/20G06N5/00
CPCG06Q30/0202G06Q50/30G06N20/20G06N5/01
Inventor 周明思俞剑男
Owner CTRIP TRAVEL NETWORK TECH SHANGHAI0
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap